CN111652476A - Technology for detecting cheating during course brushing on online learning platform - Google Patents
Technology for detecting cheating during course brushing on online learning platform Download PDFInfo
- Publication number
- CN111652476A CN111652476A CN202010407501.7A CN202010407501A CN111652476A CN 111652476 A CN111652476 A CN 111652476A CN 202010407501 A CN202010407501 A CN 202010407501A CN 111652476 A CN111652476 A CN 111652476A
- Authority
- CN
- China
- Prior art keywords
- time
- playing
- data
- platform
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention discloses a technology for detecting lesson-brushing cheating on an online learning platform, which comprises the following detection processes: when a student logs in an APP or WEB end webpage for learning and opens a playing video, a platform firstly detects the watching playing time length of a user and the video interval playing time point by adopting timing heartbeat; recording the playing records into a database in a queue mode, simultaneously monitoring a binlog log of the database in real time by a big data platform, and synchronizing data to a data center; capturing SPARK for data analysis, monitoring database data in real time by a big data item through SPARK, subtracting adjacent insertion records in two times through real-time calculation to obtain a difference value, and comparing the difference value with the submitted playing time, wherein if the adjacent time difference in two times is smaller than the submitted playing time, a user has a course brushing behavior. Has the advantages that: the invention can accurately grab and brush students to perform guidance and deterrence, improve the teaching quality and improve the MOOC learning quality.
Description
Technical Field
The invention relates to the field of network learning, in particular to a technology for detecting cheating during class brushing on an online learning platform.
Background
At present, online learning has become the trend, and education portion grabs the learning quality deeply, but when student study net class at present, the machine is brushed class seriously, and education quality descends, and we can collect user's learning video record heartbeat, through data record, whether big data detection machine learning, improve the teaching quality, strike and brush class.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
In order to improve the learning quality of MOOC teaching, the learning behaviors of users are analyzed through big data, whether the learning is machine learning or manual learning is judged, the teaching purpose is improved, lessons brushing students are deterred, lessons brushing is reduced, and a technology for detecting lesson brushing cheating by an online learning platform is provided, so that the problems in the background technology are solved.
In order to achieve the purpose, the invention provides the following technical scheme: a technology for detecting cheating during class brushing on an online learning platform comprises the following detection processes:
(1) when a student logs in an APP or WEB end webpage for learning, and opens a playing video, a platform firstly detects the user watching playing time and the video interval playing time point by timing heartbeat, the heartbeat submits a learning progress, the learning progress record comprises key information such as a user ID, the user playing time, the user video playing time point, a video ID, creation time and the like, and the key information is stored in a database through an MQ queue;
(2) recording the playing records into a database in a queue mode, simultaneously monitoring the binlog log of the database in real time by a large data platform (the video watching record data of a platform user every day is calculated by taking billions as a unit), and synchronizing the data to a data center;
(3) capturing SPARK for data analysis, monitoring database data in real time by a big data item through SPARK, subtracting adjacent insertion records in two times through real-time calculation to obtain a difference value, and comparing the difference value with the submitted playing time, wherein if the adjacent time difference in two times is smaller than the submitted playing time, a user has a course brushing behavior.
Further, the principle of cheating rule analysis is as follows: firstly, the design column of the student watching log table comprises: user ID, course ID, the video playing time of this time, and creation time field, and then the big data system passes through the captured binlog log.
Furthermore, the student watches are grouped and sorted according to the creation time, and the two times of creation time are subtracted by using a big data internal function to obtain the actual record playing time and the actual record submitting time for comparison.
Furthermore, if the time length of each time of watching by the student is longer than the difference of the watching records submitted twice, the fact that the submitted data has a course brushing behavior is shown.
Furthermore, the big data platform puts students into an abnormal queue, submits the analyzed playing record data to the abnormal queue, and stores and reserves files.
Compared with the prior art, the invention has the following beneficial effects: the invention can accurately grab and brush students to perform guidance and deterrence, improve the teaching quality and improve the MOOC learning quality.
Detailed Description
The invention will be further described with reference to specific embodiments:
the technology for detecting the cheating of lessons by the online learning platform according to the embodiment of the invention comprises the following detection processes:
(1) when a student logs in an APP or WEB end webpage for learning, and opens a playing video, a platform firstly detects the user watching playing time and the video interval playing time point by timing heartbeat, the heartbeat submits a learning progress, the learning progress record comprises key information such as a user ID, the user playing time, the user video playing time point, a video ID, creation time and the like, and the key information is stored in a database through an MQ queue;
(2) recording the playing records into a database in a queue mode, simultaneously monitoring the binlog log of the database in real time by a large data platform (the video watching record data of a platform user every day is calculated by taking billions as a unit), and synchronizing the data to a data center;
(3) capturing SPARK for data analysis, monitoring database data in real time by a big data item through SPARK, subtracting adjacent insertion records in two times through real-time calculation to obtain a difference value, and comparing the difference value with the submitted playing time, wherein if the adjacent time difference in two times is smaller than the submitted playing time, a user has a course brushing behavior.
Principle of cheating rule analysis: firstly, the design column of the student watching log table comprises: the method comprises the steps that a user ID, a course ID, the video playing time and a creation time field are obtained, then a big data system groups student watching through a captured binlog log and sorts the student watching according to the creation time, the creation time at two intervals is subtracted by using a big data internal function to obtain the recorded actual playing time and the submitted time to be compared, and if the watching time of the student is longer than the watching record difference submitted twice, the fact that the submitted data has a course brushing behavior is shown. And the big data platform puts the students into an abnormal queue, submits the analyzed playing record data to the abnormal queue, and stores and reserves files. For example, the first time of submitting a record is 10 o 'clock 08 minutes, the record is played for 60 seconds, the creation time of the next record is after 10 o' clock 09 minutes, and if the time of the database record is between 10 o 'clock 09 minutes and 10 o' clock 08 minutes, the lesson brushing is determined. Whether to brush lessons is detected by detecting the difference value of the time points of the student submitting records and the time points of the student playing.
When the method is applied specifically, students log in an MOOC learning platform, learn MOOC videos through WEB terminals or mobile phone equipment, submit learning progress through heartbeat, record learning progress includes key information such as user IDs, user playing time, user video playing time points, video IDs, creating time and the like, and store the key information in a database through MQ queues. The big data item monitors database data in real time through SPARK, difference values obtained by subtracting adjacent insertion records in two times are compared with the submitted playing time through real-time calculation, and if the adjacent time difference in two times is smaller than the submitted playing time, a user has a course brushing behavior.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that various changes, modifications and substitutions can be made without departing from the spirit and scope of the invention as defined by the appended claims. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. The technology for detecting the cheating of lessons by the online learning platform is characterized by comprising the following detection processes:
(1) when a student logs in an APP or WEB end webpage for learning, and opens a playing video, a platform firstly detects the user watching playing time and the video interval playing time point by timing heartbeat, the heartbeat submits a learning progress, the learning progress record comprises key information such as a user ID, the user playing time, the user video playing time point, a video ID, creation time and the like, and the key information is stored in a database through an MQ queue;
(2) recording the playing records into a database in a queue mode, simultaneously monitoring the binlog log of the database in real time by a large data platform (the video watching record data of a platform user every day is calculated by taking billions as a unit), and synchronizing the data to a data center;
(3) capturing SPARK for data analysis, monitoring database data in real time by a big data item through SPARK, subtracting adjacent insertion records in two times through real-time calculation to obtain a difference value, and comparing the difference value with the submitted playing time, wherein if the adjacent time difference in two times is smaller than the submitted playing time, a user has a course brushing behavior.
2. The technology for detecting cheating lessons on online learning platform as claimed in claim 1, wherein the cheating rule analysis principle is as follows: firstly, the design column of the student watching log table comprises: user ID, course ID, the video playing time of this time, and creation time field, and then the big data system passes through the captured binlog log.
3. The technology for detecting cheating during lesson brushing of the online learning platform as claimed in claim 2, wherein the students watch and group according to the creation time sequence, and the two creation time intervals are subtracted by using a big data internal function to obtain the actual playing time of the record and the submission time for comparison.
4. The technology for detecting cheating during lesson brushing on an online learning platform as claimed in claim 3, wherein if the duration of each viewing by the student is longer than the difference between the viewing records submitted twice, the submitted data is proved to have the behavior of lesson brushing.
5. The technology for detecting cheating during lesson brushing on an online learning platform as claimed in claim 4, wherein the big data platform puts students into an abnormal queue, and simultaneously submits the analyzed playing record data to the abnormal queue for storage and retention.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010407501.7A CN111652476A (en) | 2020-05-14 | 2020-05-14 | Technology for detecting cheating during course brushing on online learning platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010407501.7A CN111652476A (en) | 2020-05-14 | 2020-05-14 | Technology for detecting cheating during course brushing on online learning platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111652476A true CN111652476A (en) | 2020-09-11 |
Family
ID=72346602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010407501.7A Pending CN111652476A (en) | 2020-05-14 | 2020-05-14 | Technology for detecting cheating during course brushing on online learning platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652476A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570946A (en) * | 2021-07-21 | 2021-10-29 | 北京思想天下教育科技有限公司 | Online training education informatization teaching method and system based on big data cloud platform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104410906A (en) * | 2014-11-18 | 2015-03-11 | 北京国双科技有限公司 | Detection method and detection device for video playing behavior |
| CN104410873A (en) * | 2014-11-19 | 2015-03-11 | 北京国双科技有限公司 | Method and device of detecting number of television channel users |
| CN109241302A (en) * | 2018-08-31 | 2019-01-18 | 深圳市轱辘汽车维修技术有限公司 | A kind of comment authorization method, device and the terminal device of online course |
| CN109274994A (en) * | 2018-12-03 | 2019-01-25 | 湖北美和易思教育科技有限公司 | Online education platform vod data Statistical monitor system |
| CN109636690A (en) * | 2018-12-17 | 2019-04-16 | 中国人民解放军国防科技大学 | Learning effectiveness comprehensive scoring method based on online learning behavior data of learner |
| CN109753531A (en) * | 2018-12-26 | 2019-05-14 | 深圳市麦谷科技有限公司 | A kind of big data statistical method, system, computer equipment and storage medium |
| CN110738114A (en) * | 2019-01-24 | 2020-01-31 | 中铁三局集团有限公司 | student identity safety verification system for online education |
| CN110782375A (en) * | 2019-09-05 | 2020-02-11 | 华南师范大学 | Online learning overall process dynamic analysis method and system based on data |
-
2020
- 2020-05-14 CN CN202010407501.7A patent/CN111652476A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104410906A (en) * | 2014-11-18 | 2015-03-11 | 北京国双科技有限公司 | Detection method and detection device for video playing behavior |
| CN104410873A (en) * | 2014-11-19 | 2015-03-11 | 北京国双科技有限公司 | Method and device of detecting number of television channel users |
| CN109241302A (en) * | 2018-08-31 | 2019-01-18 | 深圳市轱辘汽车维修技术有限公司 | A kind of comment authorization method, device and the terminal device of online course |
| CN109274994A (en) * | 2018-12-03 | 2019-01-25 | 湖北美和易思教育科技有限公司 | Online education platform vod data Statistical monitor system |
| CN109636690A (en) * | 2018-12-17 | 2019-04-16 | 中国人民解放军国防科技大学 | Learning effectiveness comprehensive scoring method based on online learning behavior data of learner |
| CN109753531A (en) * | 2018-12-26 | 2019-05-14 | 深圳市麦谷科技有限公司 | A kind of big data statistical method, system, computer equipment and storage medium |
| CN110738114A (en) * | 2019-01-24 | 2020-01-31 | 中铁三局集团有限公司 | student identity safety verification system for online education |
| CN110782375A (en) * | 2019-09-05 | 2020-02-11 | 华南师范大学 | Online learning overall process dynamic analysis method and system based on data |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570946A (en) * | 2021-07-21 | 2021-10-29 | 北京思想天下教育科技有限公司 | Online training education informatization teaching method and system based on big data cloud platform |
| CN113570946B (en) * | 2021-07-21 | 2022-06-28 | 北京思想天下教育科技有限公司 | Online training education informatization teaching method and system based on big data cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9633572B2 (en) | Systems and methods for computerized interactive skill training | |
| CN109582645B (en) | Anti-cheating system for paperless examination | |
| US20050053902A1 (en) | Method for working out the behavioural strategy of a player using a cognitive virtual reality, device for carrying out said method and an information-carrying medium for said device | |
| CN108171414A (en) | Evaluation System for Teaching Quality | |
| Vitiello et al. | User Behavioral Patterns and Early Dropouts Detection: Improved Users Profiling through Analysis of Successive Offering of MOOC. | |
| CN110751861B (en) | Network remote education system based on cloud platform | |
| CN109559580B (en) | Online learning system | |
| CN113781853A (en) | Teacher-student remote interactive education platform based on terminal | |
| CN111652476A (en) | Technology for detecting cheating during course brushing on online learning platform | |
| CN116229777A (en) | Internet comprehensive teaching training method, system, medium and equipment | |
| May | Number Talks Benefit Fifth Graders' Numeracy. | |
| CN110991800A (en) | Piano teaching quality evaluation system | |
| CN111028583A (en) | Remote network teaching system and method | |
| CN114512041A (en) | Teaching action big data analysis device based on panorama is made a video recording | |
| CN112288901A (en) | Online video learning card punching test method | |
| CN114971975A (en) | Learning abnormity prompting method and system for online education platform | |
| CN115278272A (en) | Education practice online guidance system and method | |
| CN113065510A (en) | Competition answer state monitoring method | |
| CN113327183A (en) | Teaching system based on block chain and teaching resource sharing method | |
| Shurtina et al. | LEARNERS’INTERACTIONS IN MASSIVE OPEN ONLINE COURSES: ANALYSIS AND INTERPRETATION | |
| Marciel et al. | Enhancements to Google Course Builder: assessments visualisation, YouTube events collector and dummy data generator | |
| Vitiello et al. | Predicting dropouts on the successive offering of a MOOC | |
| Larionova et al. | Students behavioural patterns on the national open education platform | |
| Riel et al. | Is anyone watching the course video? Inferring elapsed watch time and video engagement patterns when using embedded videos from YouTube, Vimeo, or other third-party video streaming services for Moodle and other online learning management systems | |
| Liz-Domínguez et al. | Assessing the Importance of Video Visualization Timings in a Flipped Classroom Context |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 901, 902, 903, 904, building 1, 1188 Qinzhou North Road, Xuhui District, Shanghai 200000 Applicant after: Shanghai Zhuoyue Ruixin Digital Technology Co.,Ltd. Address before: Room 901, 902, 903, 904, building 1, 1188 Qinzhou North Road, Xuhui District, Shanghai 200000 Applicant before: SHANGHAI ABLE DIGITAL & TECH Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200911 |